{"total":93,"rows":[{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2507.02833","title":"Generalizing Verifiable Instruction Following","created":"2025-07-03","cited_by_count":194,"area":null},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2506.18254","title":"RLPR: Extrapolating RLVR to General Domains without Verifiers","created":"2025-06-23","cited_by_count":85,"area":"lr"},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2506.09501","title":"Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference","created":"2025-06-11","cited_by_count":53,"area":null},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2506.09014","title":"Learning to Reason Across Parallel Samples for LLM Reasoning","created":"2025-06-10","cited_by_count":32,"area":"lr"},{"id":"2505.03981","title":"X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains","created":"2025-05-06","cited_by_count":31,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2507.04103","title":"How to Train Your LLM Web Agent: A Statistical Diagnosis","created":"2025-07-05","cited_by_count":19,"area":"agents"},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.21067","title":"Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2506.15707","title":"Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling","created":"2025-05-30","cited_by_count":15,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2505.13109","title":"FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference","created":"2025-05-19","cited_by_count":14,"area":"inference"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2507.10541","title":"REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once","created":"2025-07-14","cited_by_count":12,"area":"lr"},{"id":"2509.00084","title":"Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs","created":"2025-08-27","cited_by_count":12,"area":"lr"},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2506.12353","title":"Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2601.02316","title":"DatBench: Discriminative, Faithful, and Efficient VLM Evaluations","created":"2026-01-05","cited_by_count":10,"area":null},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2507.15865","title":"From Reasoning to Super-Intelligence: A Search-Theoretic Perspective","created":"2025-07-13","cited_by_count":9,"area":"lr"},{"id":"2512.07795","title":"ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning","created":"2025-12-08","cited_by_count":9,"area":"lr"},{"id":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"area":"lr"},{"id":"2604.18419","title":"Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning","created":"2026-04-20","cited_by_count":8,"area":"lr"},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2505.14147","title":"SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning","created":"2025-05-20","cited_by_count":5,"area":"lr"},{"id":"2506.04913","title":"Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study","created":"2025-06-05","cited_by_count":5,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2508.20384","title":"Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM","created":"2025-08-28","cited_by_count":5,"area":"lr"},{"id":"2504.11711","title":"The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs","created":"2025-04-16","cited_by_count":4,"area":null},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2506.10378","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2511.21005","title":"ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2506.03295","title":"Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem","created":"2025-06-03","cited_by_count":3,"area":"lr"},{"id":"2506.04734","title":"Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design","created":"2025-06-05","cited_by_count":3,"area":"lr"},{"id":"2507.07765","title":"Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2509.21173","title":"Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2510.20272","title":"Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2511.07722","title":"Critical Confabulation: Can LLMs Hallucinate for Social Good?","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2511.16655","title":"Solving Spatial Supersensing Without Spatial Supersensing","created":"2025-11-20","cited_by_count":2,"area":"wm"},{"id":"2512.14079","title":"Grammar Search for Multi-Agent Systems","created":"2025-12-16","cited_by_count":2,"area":"agents"},{"id":"2605.22156","title":"One-Way Policy Optimization for Self-Evolving LLMs","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2505.12058","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2508.01245","title":"WarriorMath: Enhancing the Mathematical Ability of Large Language Models with a Defect-aware Framework","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2609.36931","title":"Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2508.03872","title":"Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.25941","title":"Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2512.14237","title":"Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.14761","title":"CAPE: Capability Achievement via Policy Execution","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.11782","title":"FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.11996","title":"Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.09806","title":"LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.29888","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.26094","title":"RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.06012","title":"HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.25936","title":"One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.06671","title":"Tracking the Moving Frontier: Long-Short Term Advantage Estimator","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.15476","title":"Temperature Fragility and the Conditional Benefits of Truncation Sampling","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36569","title":"From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36587","title":"Learned Reporting Preferences in RLVR Can Conflict with the Current Request","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02911","title":"Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13287","title":"Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15570","title":"Truncation Samplers Are Nested: Comparing Decoding Rules Is a Measurement Problem","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}